Various distributions are adding or are in the process of adding support
for system extensions and in the future configuration extensions through
various tools. A more detailed explanation on system and configuration
extensions can be found on the manpage which is listed below at [1].
System extension images may – dynamically at runtime — extend the /usr/
and /opt/ directory hierarchies with additional files. This is
particularly useful on immutable system images where a /usr/ and/or
/opt/ hierarchy residing on a read-only file system shall be extended
temporarily at runtime without making any persistent modifications.
When one or more system extension images are activated, their /usr/ and
/opt/ hierarchies are combined via overlayfs with the same hierarchies
of the host OS, and the host /usr/ and /opt/ overmounted with it
("merging"). When they are deactivated, the mount point is disassembled
— again revealing the unmodified original host version of the hierarchy
("unmerging"). Merging thus makes the extension's resources suddenly
appear below the /usr/ and /opt/ hierarchies as if they were included in
the base OS image itself. Unmerging makes them disappear again, leaving
in place only the files that were shipped with the base OS image itself.
System configuration images are similar but operate on directories
containing system or service configuration.
On nearly all modern distributions mount propagation plays a crucial
role and the rootfs of the OS is a shared mount in a peer group (usually
with peer group id 1):
TARGET SOURCE FSTYPE PROPAGATION MNT_ID PARENT_ID
/ / ext4 shared:1 29 1
On such systems all services and containers run in a separate mount
namespace and are pivot_root()ed into their rootfs. A separate mount
namespace is almost always used as it is the minimal isolation mechanism
services have. But usually they are even much more isolated up to the
point where they almost become indistinguishable from containers.
Mount propagation again plays a crucial role here. The rootfs of all
these services is a slave mount to the peer group of the host rootfs.
This is done so the service will receive mount propagation events from
the host when certain files or directories are updated.
In addition, the rootfs of each service, container, and sandbox is also
a shared mount in its separate peer group:
TARGET SOURCE FSTYPE PROPAGATION MNT_ID PARENT_ID
/ / ext4 shared:24 master:1 71 47
For people not too familiar with mount propagation, the master:1 means
that this is a slave mount to peer group 1. Which as one can see is the
host rootfs as indicated by shared:1 above. The shared:24 indicates that
the service rootfs is a shared mount in a separate peer group with peer
group id 24.
A service may run other services. Such nested services will also have a
rootfs mount that is a slave to the peer group of the outer service
rootfs mount.
For containers things are just slighly different. A container's rootfs
isn't a slave to the service's or host rootfs' peer group. The rootfs
mount of a container is simply a shared mount in its own peer group:
TARGET SOURCE FSTYPE PROPAGATION MNT_ID PARENT_ID
/home/ubuntu/debian-tree / ext4 shared:99 61 60
So whereas services are isolated OS components a container is treated
like a separate world and mount propagation into it is restricted to a
single well known mount that is a slave to the peer group of the shared
mount /run on the host:
TARGET SOURCE FSTYPE PROPAGATION MNT_ID PARENT_ID
/propagate/debian-tree /run/host/incoming tmpfs master:5 71 68
Here, the master:5 indicates that this mount is a slave to the peer
group with peer group id 5. This allows to propagate mounts into the
container and served as a workaround for not being able to insert mounts
into mount namespaces directly. But the new mount api does support
inserting mounts directly. For the interested reader the blogpost in [2]
might be worth reading where I explain the old and the new approach to
inserting mounts into mount namespaces.
Containers of course, can themselves be run as services. They often run
full systems themselves which means they again run services and
containers with the exact same propagation settings explained above.
The whole system is designed so that it can be easily updated, including
all services in various fine-grained ways without having to enter every
single service's mount namespace which would be prohibitively expensive.
The mount propagation layout has been carefully chosen so it is possible
to propagate updates for system extensions and configurations from the
host into all services.
The simplest model to update the whole system is to mount on top of
/usr, /opt, or /etc on the host. The new mount on /usr, /opt, or /etc
will then propagate into every service. This works cleanly the first
time. However, when the system is updated multiple times it becomes
necessary to unmount the first update on /opt, /usr, /etc and then
propagate the new update. But this means, there's an interval where the
old base system is accessible. This has to be avoided to protect against
downgrade attacks.
The vfs already exposes a mechanism to userspace whereby mounts can be
mounted beneath an existing mount. Such mounts are internally referred
to as "tucked". The patch series exposes the ability to mount beneath a
top mount through the new MOVE_MOUNT_BENEATH flag for the move_mount()
system call. This allows userspace to seamlessly upgrade mounts. After
this series the only thing that will have changed is that mounting
beneath an existing mount can be done explicitly instead of just
implicitly.
Today, there are two scenarios where a mount can be mounted beneath an
existing mount instead of on top of it:
(1) When a service or container is started in a new mount namespace and
pivot_root()s into its new rootfs. The way this is done is by
mounting the new rootfs beneath the old rootfs:
fd_newroot = open("/var/lib/machines/fedora", ...);
fd_oldroot = open("/", ...);
fchdir(fd_newroot);
pivot_root(".", ".");
After the pivot_root(".", ".") call the new rootfs is mounted
beneath the old rootfs which can then be unmounted to reveal the
underlying mount:
fchdir(fd_oldroot);
umount2(".", MNT_DETACH);
Since pivot_root() moves the caller into a new rootfs no mounts must
be propagated out of the new rootfs as a consequence of the
pivot_root() call. Thus, the mounts cannot be shared.
(2) When a mount is propagated to a mount that already has another mount
mounted on the same dentry.
The easiest example for this is to create a new mount namespace. The
following commands will create a mount namespace where the rootfs
mount / will be a slave to the peer group of the host rootfs /
mount's peer group. IOW, it will receive propagation from the host:
mount --make-shared /
unshare --mount --propagation=slave
Now a new mount on the /mnt dentry in that mount namespace is
created. (As it can be confusing it should be spelled out that the
tmpfs mount on the /mnt dentry that was just created doesn't
propagate back to the host because the rootfs mount / of the mount
namespace isn't a peer of the host rootfs.):
mount -t tmpfs tmpfs /mnt
TARGET SOURCE FSTYPE PROPAGATION
└─/mnt tmpfs tmpfs
Now another terminal in the host mount namespace can observe that
the mount indeed hasn't propagated back to into the host mount
namespace. A new mount can now be created on top of the /mnt dentry
with the rootfs mount / as its parent:
mount --bind /opt /mnt
TARGET SOURCE FSTYPE PROPAGATION
└─/mnt /dev/sda2[/opt] ext4 shared:1
The mount namespace that was created earlier can now observe that
the bind mount created on the host has propagated into it:
TARGET SOURCE FSTYPE PROPAGATION
└─/mnt /dev/sda2[/opt] ext4 master:1
└─/mnt tmpfs tmpfs
But instead of having been mounted on top of the tmpfs mount at the
/mnt dentry the /opt mount has been mounted on top of the rootfs
mount at the /mnt dentry. And the tmpfs mount has been remounted on
top of the propagated /opt mount at the /opt dentry. So in other
words, the propagated mount has been mounted beneath the preexisting
mount in that mount namespace.
Mount namespaces make this easy to illustrate but it's also easy to
mount beneath an existing mount in the same mount namespace
(The following example assumes a shared rootfs mount / with peer
group id 1):
mount --bind /opt /opt
TARGET SOURCE FSTYPE MNT_ID PARENT_ID PROPAGATION
└─/opt /dev/sda2[/opt] ext4 188 29 shared:1
If another mount is mounted on top of the /opt mount at the /opt
dentry:
mount --bind /tmp /opt
The following clunky mount tree will result:
TARGET SOURCE FSTYPE MNT_ID PARENT_ID PROPAGATION
└─/opt /dev/sda2[/tmp] ext4 405 29 shared:1
└─/opt /dev/sda2[/opt] ext4 188 405 shared:1
└─/opt /dev/sda2[/tmp] ext4 404 188 shared:1
The /tmp mount is mounted beneath the /opt mount and another copy is
mounted on top of the /opt mount. This happens because the rootfs /
and the /opt mount are shared mounts in the same peer group.
When the new /tmp mount is supposed to be mounted at the /opt dentry
then the /tmp mount first propagates to the root mount at the /opt
dentry. But there already is the /opt mount mounted at the /opt
dentry. So the old /opt mount at the /opt dentry will be mounted on
top of the new /tmp mount at the /tmp dentry, i.e. @opt->mnt_parent
is @tmp and @opt->mnt_mountpoint is /tmp (Note that @opt->mnt_root
is /opt which is what shows up as /opt under SOURCE). So again, a
mount will be mounted beneath a preexisting mount.
(Fwiw, a few iterations of mount --bind /opt /opt in a loop on a
shared rootfs is a good example of what could be referred to as
mount explosion.)
The main point is that such mounts allows userspace to umount a top
mount and reveal an underlying mount. So for example, umounting the
tmpfs mount on /mnt that was created in example (1) using mount
namespaces reveals the /opt mount which was mounted beneath it.
In (2) where a mount was mounted beneath the top mount in the same mount
namespace unmounting the top mount would unmount both the top mount and
the mount beneath. In the process the original mount would be remounted
on top of the rootfs mount / at the /opt dentry again.
This again, is a result of mount propagation only this time it's umount
propagation. However, this can be avoided by simply making the parent
mount / of the @opt mount a private or slave mount. Then the top mount
and the original mount can be unmounted to reveal the mount beneath.
These two examples are fairly arcane and are merely added to make it
clear how mount propagation has effects on current and future features.
More common use-cases will just be things like:
mount -t btrfs /dev/sdA /mnt
mount -t xfs /dev/sdB --beneath /mnt
umount /mnt
after which we'll have updated from a btrfs filesystem to a xfs
filesystem without ever revealing the underlying mountpoint.
The crux is that the proposed mechanism already exists and that it is so
powerful as to cover cases where mounts are supposed to be updated with
new versions. Crucially, it offers an important flexibility. Namely that
updates to a system may either be forced or can be delayed and the
umount of the top mount be left to a service if it is a cooperative one.
This adds a new flag to move_mount() that allows to explicitly move a
beneath the top mount adhering to the following semantics:
* Mounts cannot be mounted beneath the rootfs. This restriction
encompasses the rootfs but also chroots via chroot() and pivot_root().
To mount a mount beneath the rootfs or a chroot, pivot_root() can be
used as illustrated above.
* The source mount must be a private mount to force the kernel to
allocate a new, unused peer group id. This isn't a required
restriction but a voluntary one. It avoids repeating a semantical
quirk that already exists today. If bind mounts which already have a
peer group id are inserted into mount trees that have the same peer
group id this can cause a lot of mount propagation events to be
generated (For example, consider running mount --bind /opt /opt in a
loop where the parent mount is a shared mount.).
* Avoid getting rid of the top mount in the kernel. Cooperative services
need to be able to unmount the top mount themselves.
This also avoids a good deal of additional complexity. The umount
would have to be propagated which would be another rather expensive
operation. So namespace_lock() and lock_mount_hash() would potentially
have to be held for a long time for both a mount and umount
propagation. That should be avoided.
* The path to mount beneath must be mounted and attached.
* The top mount and its parent must be in the caller's mount namespace
and the caller must be able to mount in that mount namespace.
* The caller must be able to unmount the top mount to prove that they
could reveal the underlying mount.
* The propagation tree is calculated based on the destination mount's
parent mount and the destination mount's mountpoint on the parent
mount. Of course, if the parent of the destination mount and the
destination mount are shared mounts in the same peer group and the
mountpoint of the new mount to be mounted is a subdir of their
->mnt_root then both will receive a mount of /opt. That's probably
easier to understand with an example. Assuming a standard shared
rootfs /:
mount --bind /opt /opt
mount --bind /tmp /opt
will cause the same mount tree as:
mount --bind /opt /opt
mount --beneath /tmp /opt
because both / and /opt are shared mounts/peers in the same peer
group and the /opt dentry is a subdirectory of both the parent's and
the child's ->mnt_root. If a mount tree like that is created it almost
always is an accident or abuse of mount propagation. Realistically
what most people probably mean in this scenarios is:
mount --bind /opt /opt
mount --make-private /opt
mount --make-shared /opt
This forces the allocation of a new separate peer group for the /opt
mount. Aferwards a mount --bind or mount --beneath actually makes
sense as the / and /opt mount belong to different peer groups. Before
that it's likely just confusion about what the user wanted to achieve.
* Refuse MOVE_MOUNT_BENEATH if:
(1) the @mnt_from has been overmounted in between path resolution and
acquiring @namespace_sem when locking @mnt_to. This avoids the
proliferation of shadow mounts.
(2) if @to_mnt is moved to a different mountpoint while acquiring
@namespace_sem to lock @to_mnt.
(3) if @to_mnt is unmounted while acquiring @namespace_sem to lock
@to_mnt.
(4) if the parent of the target mount propagates to the target mount
at the same mountpoint.
This would mean mounting @mnt_from on @mnt_to->mnt_parent and then
propagating a copy @c of @mnt_from onto @mnt_to. This defeats the
whole purpose of mounting @mnt_from beneath @mnt_to.
(5) if the parent mount @mnt_to->mnt_parent propagates to @mnt_from at
the same mountpoint.
If @mnt_to->mnt_parent propagates to @mnt_from this would mean
propagating a copy @c of @mnt_from on top of @mnt_from. Afterwards
@mnt_from would be mounted on top of @mnt_to->mnt_parent and
@mnt_to would be unmounted from @mnt->mnt_parent and remounted on
@mnt_from. But since @c is already mounted on @mnt_from, @mnt_to
would ultimately be remounted on top of @c. Afterwards, @mnt_from
would be covered by a copy @c of @mnt_from and @c would be covered
by @mnt_from itself. This defeats the whole purpose of mounting
@mnt_from beneath @mnt_to.
Cases (1) to (3) are required as they deal with races that would cause
bugs or unexpected behavior for users. Cases (4) and (5) refuse
semantical quirks that would not be a bug but would cause weird mount
trees to be created. While they can already be created via other means
(mount --bind /opt /opt x n) there's no reason to repeat past mistakes
in new features.
Link: https://man7.org/linux/man-pages/man8/systemd-sysext.8.html [1]
Link: https://brauner.io/2023/02/28/mounting-into-mount-namespaces.html [2]
Link: https://github.com/flatcar/sysext-bakery
Link: https://fedoraproject.org/wiki/Changes/Unified_Kernel_Support_Phase_1
Link: https://fedoraproject.org/wiki/Changes/Unified_Kernel_Support_Phase_2
Link: https://github.com/systemd/systemd/pull/26013
Reviewed-by: Seth Forshee (DigitalOcean) <sforshee@kernel.org>
Message-Id: <20230202-fs-move-mount-replace-v4-4-98f3d80d7eaa@kernel.org>
Signed-off-by: Christian Brauner <brauner@kernel.org>
Currently, we use a global variable to stash the destination
mountpoint. All global variables are changed in propagate_one(). The
mountpoint variable is one of the few which doesn't change after
initialization. Instead, just pass the destination mountpoint directly
making it easy to verify directly in propagate_mnt() that the
destination mountpoint never changes.
Reviewed-by: Seth Forshee (DigitalOcean) <sforshee@kernel.org>
Message-Id: <20230202-fs-move-mount-replace-v2-2-f53cd31d6392@kernel.org>
Signed-off-by: Christian Brauner <brauner@kernel.org>
The propagate_mnt() function handles mount propagation when creating
mounts and propagates the source mount tree @source_mnt to all
applicable nodes of the destination propagation mount tree headed by
@dest_mnt.
Unfortunately it contains a bug where it fails to terminate at peers of
@source_mnt when looking up copies of the source mount that become
masters for copies of the source mount tree mounted on top of slaves in
the destination propagation tree causing a NULL dereference.
Once the mechanics of the bug are understood it's easy to trigger.
Because of unprivileged user namespaces it is available to unprivileged
users.
While fixing this bug we've gotten confused multiple times due to
unclear terminology or missing concepts. So let's start this with some
clarifications:
* The terms "master" or "peer" denote a shared mount. A shared mount
belongs to a peer group.
* A peer group is a set of shared mounts that propagate to each other.
They are identified by a peer group id. The peer group id is available
in @shared_mnt->mnt_group_id.
Shared mounts within the same peer group have the same peer group id.
The peers in a peer group can be reached via @shared_mnt->mnt_share.
* The terms "slave mount" or "dependent mount" denote a mount that
receives propagation from a peer in a peer group. IOW, shared mounts
may have slave mounts and slave mounts have shared mounts as their
master. Slave mounts of a given peer in a peer group are listed on
that peers slave list available at @shared_mnt->mnt_slave_list.
* The term "master mount" denotes a mount in a peer group. IOW, it
denotes a shared mount or a peer mount in a peer group. The term
"master mount" - or "master" for short - is mostly used when talking
in the context of slave mounts that receive propagation from a master
mount. A master mount of a slave identifies the closest peer group a
slave mount receives propagation from. The master mount of a slave can
be identified via @slave_mount->mnt_master. Different slaves may point
to different masters in the same peer group.
* Multiple peers in a peer group can have non-empty ->mnt_slave_lists.
Non-empty ->mnt_slave_lists of peers don't intersect. Consequently, to
ensure all slave mounts of a peer group are visited the
->mnt_slave_lists of all peers in a peer group have to be walked.
* Slave mounts point to a peer in the closest peer group they receive
propagation from via @slave_mnt->mnt_master (see above). Together with
these peers they form a propagation group (see below). The closest
peer group can thus be identified through the peer group id
@slave_mnt->mnt_master->mnt_group_id of the peer/master that a slave
mount receives propagation from.
* A shared-slave mount is a slave mount to a peer group pg1 while also
a peer in another peer group pg2. IOW, a peer group may receive
propagation from another peer group.
If a peer group pg1 is a slave to another peer group pg2 then all
peers in peer group pg1 point to the same peer in peer group pg2 via
->mnt_master. IOW, all peers in peer group pg1 appear on the same
->mnt_slave_list. IOW, they cannot be slaves to different peer groups.
* A pure slave mount is a slave mount that is a slave to a peer group
but is not a peer in another peer group.
* A propagation group denotes the set of mounts consisting of a single
peer group pg1 and all slave mounts and shared-slave mounts that point
to a peer in that peer group via ->mnt_master. IOW, all slave mounts
such that @slave_mnt->mnt_master->mnt_group_id is equal to
@shared_mnt->mnt_group_id.
The concept of a propagation group makes it easier to talk about a
single propagation level in a propagation tree.
For example, in propagate_mnt() the immediate peers of @dest_mnt and
all slaves of @dest_mnt's peer group form a propagation group propg1.
So a shared-slave mount that is a slave in propg1 and that is a peer
in another peer group pg2 forms another propagation group propg2
together with all slaves that point to that shared-slave mount in
their ->mnt_master.
* A propagation tree refers to all mounts that receive propagation
starting from a specific shared mount.
For example, for propagate_mnt() @dest_mnt is the start of a
propagation tree. The propagation tree ecompasses all mounts that
receive propagation from @dest_mnt's peer group down to the leafs.
With that out of the way let's get to the actual algorithm.
We know that @dest_mnt is guaranteed to be a pure shared mount or a
shared-slave mount. This is guaranteed by a check in
attach_recursive_mnt(). So propagate_mnt() will first propagate the
source mount tree to all peers in @dest_mnt's peer group:
for (n = next_peer(dest_mnt); n != dest_mnt; n = next_peer(n)) {
ret = propagate_one(n);
if (ret)
goto out;
}
Notice, that the peer propagation loop of propagate_mnt() doesn't
propagate @dest_mnt itself. @dest_mnt is mounted directly in
attach_recursive_mnt() after we propagated to the destination
propagation tree.
The mount that will be mounted on top of @dest_mnt is @source_mnt. This
copy was created earlier even before we entered attach_recursive_mnt()
and doesn't concern us a lot here.
It's just important to notice that when propagate_mnt() is called
@source_mnt will not yet have been mounted on top of @dest_mnt. Thus,
@source_mnt->mnt_parent will either still point to @source_mnt or - in
the case @source_mnt is moved and thus already attached - still to its
former parent.
For each peer @m in @dest_mnt's peer group propagate_one() will create a
new copy of the source mount tree and mount that copy @child on @m such
that @child->mnt_parent points to @m after propagate_one() returns.
propagate_one() will stash the last destination propagation node @m in
@last_dest and the last copy it created for the source mount tree in
@last_source.
Hence, if we call into propagate_one() again for the next destination
propagation node @m, @last_dest will point to the previous destination
propagation node and @last_source will point to the previous copy of the
source mount tree and mounted on @last_dest.
Each new copy of the source mount tree is created from the previous copy
of the source mount tree. This will become important later.
The peer loop in propagate_mnt() is straightforward. We iterate through
the peers copying and updating @last_source and @last_dest as we go
through them and mount each copy of the source mount tree @child on a
peer @m in @dest_mnt's peer group.
After propagate_mnt() handled the peers in @dest_mnt's peer group
propagate_mnt() will propagate the source mount tree down the
propagation tree that @dest_mnt's peer group propagates to:
for (m = next_group(dest_mnt, dest_mnt); m;
m = next_group(m, dest_mnt)) {
/* everything in that slave group */
n = m;
do {
ret = propagate_one(n);
if (ret)
goto out;
n = next_peer(n);
} while (n != m);
}
The next_group() helper will recursively walk the destination
propagation tree, descending into each propagation group of the
propagation tree.
The important part is that it takes care to propagate the source mount
tree to all peers in the peer group of a propagation group before it
propagates to the slaves to those peers in the propagation group. IOW,
it creates and mounts copies of the source mount tree that become
masters before it creates and mounts copies of the source mount tree
that become slaves to these masters.
It is important to remember that propagating the source mount tree to
each mount @m in the destination propagation tree simply means that we
create and mount new copies @child of the source mount tree on @m such
that @child->mnt_parent points to @m.
Since we know that each node @m in the destination propagation tree
headed by @dest_mnt's peer group will be overmounted with a copy of the
source mount tree and since we know that the propagation properties of
each copy of the source mount tree we create and mount at @m will mostly
mirror the propagation properties of @m. We can use that information to
create and mount the copies of the source mount tree that become masters
before their slaves.
The easy case is always when @m and @last_dest are peers in a peer group
of a given propagation group. In that case we know that we can simply
copy @last_source without having to figure out what the master for the
new copy @child of the source mount tree needs to be as we've done that
in a previous call to propagate_one().
The hard case is when we're dealing with a slave mount or a shared-slave
mount @m in a destination propagation group that we need to create and
mount a copy of the source mount tree on.
For each propagation group in the destination propagation tree we
propagate the source mount tree to we want to make sure that the copies
@child of the source mount tree we create and mount on slaves @m pick an
ealier copy of the source mount tree that we mounted on a master @m of
the destination propagation group as their master. This is a mouthful
but as far as we can tell that's the core of it all.
But, if we keep track of the masters in the destination propagation tree
@m we can use the information to find the correct master for each copy
of the source mount tree we create and mount at the slaves in the
destination propagation tree @m.
Let's walk through the base case as that's still fairly easy to grasp.
If we're dealing with the first slave in the propagation group that
@dest_mnt is in then we don't yet have marked any masters in the
destination propagation tree.
We know the master for the first slave to @dest_mnt's peer group is
simple @dest_mnt. So we expect this algorithm to yield a copy of the
source mount tree that was mounted on a peer in @dest_mnt's peer group
as the master for the copy of the source mount tree we want to mount at
the first slave @m:
for (n = m; ; n = p) {
p = n->mnt_master;
if (p == dest_master || IS_MNT_MARKED(p))
break;
}
For the first slave we walk the destination propagation tree all the way
up to a peer in @dest_mnt's peer group. IOW, the propagation hierarchy
can be walked by walking up the @mnt->mnt_master hierarchy of the
destination propagation tree @m. We will ultimately find a peer in
@dest_mnt's peer group and thus ultimately @dest_mnt->mnt_master.
Btw, here the assumption we listed at the beginning becomes important.
Namely, that peers in a peer group pg1 that are slaves in another peer
group pg2 appear on the same ->mnt_slave_list. IOW, all slaves who are
peers in peer group pg1 point to the same peer in peer group pg2 via
their ->mnt_master. Otherwise the termination condition in the code
above would be wrong and next_group() would be broken too.
So the first iteration sets:
n = m;
p = n->mnt_master;
such that @p now points to a peer or @dest_mnt itself. We walk up one
more level since we don't have any marked mounts. So we end up with:
n = dest_mnt;
p = dest_mnt->mnt_master;
If @dest_mnt's peer group is not slave to another peer group then @p is
now NULL. If @dest_mnt's peer group is a slave to another peer group
then @p now points to @dest_mnt->mnt_master points which is a master
outside the propagation tree we're dealing with.
Now we need to figure out the master for the copy of the source mount
tree we're about to create and mount on the first slave of @dest_mnt's
peer group:
do {
struct mount *parent = last_source->mnt_parent;
if (last_source == first_source)
break;
done = parent->mnt_master == p;
if (done && peers(n, parent))
break;
last_source = last_source->mnt_master;
} while (!done);
We know that @last_source->mnt_parent points to @last_dest and
@last_dest is the last peer in @dest_mnt's peer group we propagated to
in the peer loop in propagate_mnt().
Consequently, @last_source is the last copy we created and mount on that
last peer in @dest_mnt's peer group. So @last_source is the master we
want to pick.
We know that @last_source->mnt_parent->mnt_master points to
@last_dest->mnt_master. We also know that @last_dest->mnt_master is
either NULL or points to a master outside of the destination propagation
tree and so does @p. Hence:
done = parent->mnt_master == p;
is trivially true in the base condition.
We also know that for the first slave mount of @dest_mnt's peer group
that @last_dest either points @dest_mnt itself because it was
initialized to:
last_dest = dest_mnt;
at the beginning of propagate_mnt() or it will point to a peer of
@dest_mnt in its peer group. In both cases it is guaranteed that on the
first iteration @n and @parent are peers (Please note the check for
peers here as that's important.):
if (done && peers(n, parent))
break;
So, as we expected, we select @last_source, which referes to the last
copy of the source mount tree we mounted on the last peer in @dest_mnt's
peer group, as the master of the first slave in @dest_mnt's peer group.
The rest is taken care of by clone_mnt(last_source, ...). We'll skip
over that part otherwise this becomes a blogpost.
At the end of propagate_mnt() we now mark @m->mnt_master as the first
master in the destination propagation tree that is distinct from
@dest_mnt->mnt_master. IOW, we mark @dest_mnt itself as a master.
By marking @dest_mnt or one of it's peers we are able to easily find it
again when we later lookup masters for other copies of the source mount
tree we mount copies of the source mount tree on slaves @m to
@dest_mnt's peer group. This, in turn allows us to find the master we
selected for the copies of the source mount tree we mounted on master in
the destination propagation tree again.
The important part is to realize that the code makes use of the fact
that the last copy of the source mount tree stashed in @last_source was
mounted on top of the previous destination propagation node @last_dest.
What this means is that @last_source allows us to walk the destination
propagation hierarchy the same way each destination propagation node @m
does.
If we take @last_source, which is the copy of @source_mnt we have
mounted on @last_dest in the previous iteration of propagate_one(), then
we know @last_source->mnt_parent points to @last_dest but we also know
that as we walk through the destination propagation tree that
@last_source->mnt_master will point to an earlier copy of the source
mount tree we mounted one an earlier destination propagation node @m.
IOW, @last_source->mnt_parent will be our hook into the destination
propagation tree and each consecutive @last_source->mnt_master will lead
us to an earlier propagation node @m via
@last_source->mnt_master->mnt_parent.
Hence, by walking up @last_source->mnt_master, each of which is mounted
on a node that is a master @m in the destination propagation tree we can
also walk up the destination propagation hierarchy.
So, for each new destination propagation node @m we use the previous
copy of @last_source and the fact it's mounted on the previous
propagation node @last_dest via @last_source->mnt_master->mnt_parent to
determine what the master of the new copy of @last_source needs to be.
The goal is to find the _closest_ master that the new copy of the source
mount tree we are about to create and mount on a slave @m in the
destination propagation tree needs to pick. IOW, we want to find a
suitable master in the propagation group.
As the propagation structure of the source mount propagation tree we
create mirrors the propagation structure of the destination propagation
tree we can find @m's closest master - i.e., a marked master - which is
a peer in the closest peer group that @m receives propagation from. We
store that closest master of @m in @p as before and record the slave to
that master in @n
We then search for this master @p via @last_source by walking up the
master hierarchy starting from the last copy of the source mount tree
stored in @last_source that we created and mounted on the previous
destination propagation node @m.
We will try to find the master by walking @last_source->mnt_master and
by comparing @last_source->mnt_master->mnt_parent->mnt_master to @p. If
we find @p then we can figure out what earlier copy of the source mount
tree needs to be the master for the new copy of the source mount tree
we're about to create and mount at the current destination propagation
node @m.
If @last_source->mnt_master->mnt_parent and @n are peers then we know
that the closest master they receive propagation from is
@last_source->mnt_master->mnt_parent->mnt_master. If not then the
closest immediate peer group that they receive propagation from must be
one level higher up.
This builds on the earlier clarification at the beginning that all peers
in a peer group which are slaves of other peer groups all point to the
same ->mnt_master, i.e., appear on the same ->mnt_slave_list, of the
closest peer group that they receive propagation from.
However, terminating the walk has corner cases.
If the closest marked master for a given destination node @m cannot be
found by walking up the master hierarchy via @last_source->mnt_master
then we need to terminate the walk when we encounter @source_mnt again.
This isn't an arbitrary termination. It simply means that the new copy
of the source mount tree we're about to create has a copy of the source
mount tree we created and mounted on a peer in @dest_mnt's peer group as
its master. IOW, @source_mnt is the peer in the closest peer group that
the new copy of the source mount tree receives propagation from.
We absolutely have to stop @source_mnt because @last_source->mnt_master
either points outside the propagation hierarchy we're dealing with or it
is NULL because @source_mnt isn't a shared-slave.
So continuing the walk past @source_mnt would cause a NULL dereference
via @last_source->mnt_master->mnt_parent. And so we have to stop the
walk when we encounter @source_mnt again.
One scenario where this can happen is when we first handled a series of
slaves of @dest_mnt's peer group and then encounter peers in a new peer
group that is a slave to @dest_mnt's peer group. We handle them and then
we encounter another slave mount to @dest_mnt that is a pure slave to
@dest_mnt's peer group. That pure slave will have a peer in @dest_mnt's
peer group as its master. Consequently, the new copy of the source mount
tree will need to have @source_mnt as it's master. So we walk the
propagation hierarchy all the way up to @source_mnt based on
@last_source->mnt_master.
So terminate on @source_mnt, easy peasy. Except, that the check misses
something that the rest of the algorithm already handles.
If @dest_mnt has peers in it's peer group the peer loop in
propagate_mnt():
for (n = next_peer(dest_mnt); n != dest_mnt; n = next_peer(n)) {
ret = propagate_one(n);
if (ret)
goto out;
}
will consecutively update @last_source with each previous copy of the
source mount tree we created and mounted at the previous peer in
@dest_mnt's peer group. So after that loop terminates @last_source will
point to whatever copy of the source mount tree was created and mounted
on the last peer in @dest_mnt's peer group.
Furthermore, if there is even a single additional peer in @dest_mnt's
peer group then @last_source will __not__ point to @source_mnt anymore.
Because, as we mentioned above, @dest_mnt isn't even handled in this
loop but directly in attach_recursive_mnt(). So it can't even accidently
come last in that peer loop.
So the first time we handle a slave mount @m of @dest_mnt's peer group
the copy of the source mount tree we create will make the __last copy of
the source mount tree we created and mounted on the last peer in
@dest_mnt's peer group the master of the new copy of the source mount
tree we create and mount on the first slave of @dest_mnt's peer group__.
But this means that the termination condition that checks for
@source_mnt is wrong. The @source_mnt cannot be found anymore by
propagate_one(). Instead it will find the last copy of the source mount
tree we created and mounted for the last peer of @dest_mnt's peer group
again. And that is a peer of @source_mnt not @source_mnt itself.
IOW, we fail to terminate the loop correctly and ultimately dereference
@last_source->mnt_master->mnt_parent. When @source_mnt's peer group
isn't slave to another peer group then @last_source->mnt_master is NULL
causing the splat below.
For example, assume @dest_mnt is a pure shared mount and has three peers
in its peer group:
===================================================================================
mount-id mount-parent-id peer-group-id
===================================================================================
(@dest_mnt) mnt_master[216] 309 297 shared:216
\
(@source_mnt) mnt_master[218]: 609 609 shared:218
(1) mnt_master[216]: 607 605 shared:216
\
(P1) mnt_master[218]: 624 607 shared:218
(2) mnt_master[216]: 576 574 shared:216
\
(P2) mnt_master[218]: 625 576 shared:218
(3) mnt_master[216]: 545 543 shared:216
\
(P3) mnt_master[218]: 626 545 shared:218
After this sequence has been processed @last_source will point to (P3),
the copy generated for the third peer in @dest_mnt's peer group we
handled. So the copy of the source mount tree (P4) we create and mount
on the first slave of @dest_mnt's peer group:
===================================================================================
mount-id mount-parent-id peer-group-id
===================================================================================
mnt_master[216] 309 297 shared:216
/
/
(S0) mnt_slave 483 481 master:216
\
\ (P3) mnt_master[218] 626 545 shared:218
\ /
\/
(P4) mnt_slave 627 483 master:218
will pick the last copy of the source mount tree (P3) as master, not (S0).
When walking the propagation hierarchy via @last_source's master
hierarchy we encounter (P3) but not (S0), i.e., @source_mnt.
We can fix this in multiple ways:
(1) By setting @last_source to @source_mnt after we processed the peers
in @dest_mnt's peer group right after the peer loop in
propagate_mnt().
(2) By changing the termination condition that relies on finding exactly
@source_mnt to finding a peer of @source_mnt.
(3) By only moving @last_source when we actually venture into a new peer
group or some clever variant thereof.
The first two options are minimally invasive and what we want as a fix.
The third option is more intrusive but something we'd like to explore in
the near future.
This passes all LTP tests and specifically the mount propagation
testsuite part of it. It also holds up against all known reproducers of
this issues.
Final words.
First, this is a clever but __worringly__ underdocumented algorithm.
There isn't a single detailed comment to be found in next_group(),
propagate_one() or anywhere else in that file for that matter. This has
been a giant pain to understand and work through and a bug like this is
insanely difficult to fix without a detailed understanding of what's
happening. Let's not talk about the amount of time that was sunk into
fixing this.
Second, all the cool kids with access to
unshare --mount --user --map-root --propagation=unchanged
are going to have a lot of fun. IOW, triggerable by unprivileged users
while namespace_lock() lock is held.
[ 115.848393] BUG: kernel NULL pointer dereference, address: 0000000000000010
[ 115.848967] #PF: supervisor read access in kernel mode
[ 115.849386] #PF: error_code(0x0000) - not-present page
[ 115.849803] PGD 0 P4D 0
[ 115.850012] Oops: 0000 [#1] PREEMPT SMP PTI
[ 115.850354] CPU: 0 PID: 15591 Comm: mount Not tainted 6.1.0-rc7 #3
[ 115.850851] Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS
VirtualBox 12/01/2006
[ 115.851510] RIP: 0010:propagate_one.part.0+0x7f/0x1a0
[ 115.851924] Code: 75 eb 4c 8b 05 c2 25 37 02 4c 89 ca 48 8b 4a 10
49 39 d0 74 1e 48 3b 81 e0 00 00 00 74 26 48 8b 92 e0 00 00 00 be 01
00 00 00 <48> 8b 4a 10 49 39 d0 75 e2 40 84 f6 74 38 4c 89 05 84 25 37
02 4d
[ 115.853441] RSP: 0018:ffffb8d5443d7d50 EFLAGS: 00010282
[ 115.853865] RAX: ffff8e4d87c41c80 RBX: ffff8e4d88ded780 RCX: ffff8e4da4333a00
[ 115.854458] RDX: 0000000000000000 RSI: 0000000000000001 RDI: ffff8e4d88ded780
[ 115.855044] RBP: ffff8e4d88ded780 R08: ffff8e4da4338000 R09: ffff8e4da43388c0
[ 115.855693] R10: 0000000000000002 R11: ffffb8d540158000 R12: ffffb8d5443d7da8
[ 115.856304] R13: ffff8e4d88ded780 R14: 0000000000000000 R15: 0000000000000000
[ 115.856859] FS: 00007f92c90c9800(0000) GS:ffff8e4dfdc00000(0000)
knlGS:0000000000000000
[ 115.857531] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 115.858006] CR2: 0000000000000010 CR3: 0000000022f4c002 CR4: 00000000000706f0
[ 115.858598] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[ 115.859393] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[ 115.860099] Call Trace:
[ 115.860358] <TASK>
[ 115.860535] propagate_mnt+0x14d/0x190
[ 115.860848] attach_recursive_mnt+0x274/0x3e0
[ 115.861212] path_mount+0x8c8/0xa60
[ 115.861503] __x64_sys_mount+0xf6/0x140
[ 115.861819] do_syscall_64+0x5b/0x80
[ 115.862117] ? do_faccessat+0x123/0x250
[ 115.862435] ? syscall_exit_to_user_mode+0x17/0x40
[ 115.862826] ? do_syscall_64+0x67/0x80
[ 115.863133] ? syscall_exit_to_user_mode+0x17/0x40
[ 115.863527] ? do_syscall_64+0x67/0x80
[ 115.863835] ? do_syscall_64+0x67/0x80
[ 115.864144] ? do_syscall_64+0x67/0x80
[ 115.864452] ? exc_page_fault+0x70/0x170
[ 115.864775] entry_SYSCALL_64_after_hwframe+0x63/0xcd
[ 115.865187] RIP: 0033:0x7f92c92b0ebe
[ 115.865480] Code: 48 8b 0d 75 4f 0c 00 f7 d8 64 89 01 48 83 c8 ff
c3 66 2e 0f 1f 84 00 00 00 00 00 90 f3 0f 1e fa 49 89 ca b8 a5 00 00
00 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d 42 4f 0c 00 f7 d8 64 89
01 48
[ 115.866984] RSP: 002b:00007fff000aa728 EFLAGS: 00000246 ORIG_RAX:
00000000000000a5
[ 115.867607] RAX: ffffffffffffffda RBX: 000055a77888d6b0 RCX: 00007f92c92b0ebe
[ 115.868240] RDX: 000055a77888d8e0 RSI: 000055a77888e6e0 RDI: 000055a77888e620
[ 115.868823] RBP: 0000000000000000 R08: 0000000000000000 R09: 0000000000000001
[ 115.869403] R10: 0000000000001000 R11: 0000000000000246 R12: 000055a77888e620
[ 115.869994] R13: 000055a77888d8e0 R14: 00000000ffffffff R15: 00007f92c93e4076
[ 115.870581] </TASK>
[ 115.870763] Modules linked in: nft_fib_inet nft_fib_ipv4
nft_fib_ipv6 nft_fib nft_reject_inet nf_reject_ipv4 nf_reject_ipv6
nft_reject nft_ct nft_chain_nat nf_nat nf_conntrack nf_defrag_ipv6
nf_defrag_ipv4 ip_set rfkill nf_tables nfnetlink qrtr snd_intel8x0
sunrpc snd_ac97_codec ac97_bus snd_pcm snd_timer intel_rapl_msr
intel_rapl_common snd vboxguest intel_powerclamp video rapl joydev
soundcore i2c_piix4 wmi fuse zram xfs vmwgfx crct10dif_pclmul
crc32_pclmul crc32c_intel polyval_clmulni polyval_generic
drm_ttm_helper ttm e1000 ghash_clmulni_intel serio_raw ata_generic
pata_acpi scsi_dh_rdac scsi_dh_emc scsi_dh_alua dm_multipath
[ 115.875288] CR2: 0000000000000010
[ 115.875641] ---[ end trace 0000000000000000 ]---
[ 115.876135] RIP: 0010:propagate_one.part.0+0x7f/0x1a0
[ 115.876551] Code: 75 eb 4c 8b 05 c2 25 37 02 4c 89 ca 48 8b 4a 10
49 39 d0 74 1e 48 3b 81 e0 00 00 00 74 26 48 8b 92 e0 00 00 00 be 01
00 00 00 <48> 8b 4a 10 49 39 d0 75 e2 40 84 f6 74 38 4c 89 05 84 25 37
02 4d
[ 115.878086] RSP: 0018:ffffb8d5443d7d50 EFLAGS: 00010282
[ 115.878511] RAX: ffff8e4d87c41c80 RBX: ffff8e4d88ded780 RCX: ffff8e4da4333a00
[ 115.879128] RDX: 0000000000000000 RSI: 0000000000000001 RDI: ffff8e4d88ded780
[ 115.879715] RBP: ffff8e4d88ded780 R08: ffff8e4da4338000 R09: ffff8e4da43388c0
[ 115.880359] R10: 0000000000000002 R11: ffffb8d540158000 R12: ffffb8d5443d7da8
[ 115.880962] R13: ffff8e4d88ded780 R14: 0000000000000000 R15: 0000000000000000
[ 115.881548] FS: 00007f92c90c9800(0000) GS:ffff8e4dfdc00000(0000)
knlGS:0000000000000000
[ 115.882234] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 115.882713] CR2: 0000000000000010 CR3: 0000000022f4c002 CR4: 00000000000706f0
[ 115.883314] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[ 115.883966] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Fixes: f2ebb3a921 ("smarter propagate_mnt()")
Fixes: 5ec0811d30 ("propogate_mnt: Handle the first propogated copy being a slave")
Cc: <stable@vger.kernel.org>
Reported-by: Ditang Chen <ditang.c@gmail.com>
Signed-off-by: Seth Forshee (Digital Ocean) <sforshee@kernel.org>
Signed-off-by: Christian Brauner (Microsoft) <brauner@kernel.org>
---
If there are no big objections I'll get this to Linus rather sooner than later.
... to protect the modification of mp->m_count done by it. Most of
the places that modify that thing also have namespace_lock held,
but not all of them can do so, so we really need mount_lock here.
Kudos to Piotr Krysiuk <piotras@gmail.com>, who'd spotted a related
bug in pivot_root(2) (fixed unnoticed in 5.3); search for other
similar turds has caught out this one.
Cc: stable@kernel.org
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
When propagating mounts across mount namespaces owned by different user
namespaces it is not possible anymore to move or umount the mount in the
less privileged mount namespace.
Here is a reproducer:
sudo mount -t tmpfs tmpfs /mnt
sudo --make-rshared /mnt
# create unprivileged user + mount namespace and preserve propagation
unshare -U -m --map-root --propagation=unchanged
# now change back to the original mount namespace in another terminal:
sudo mkdir /mnt/aaa
sudo mount -t tmpfs tmpfs /mnt/aaa
# now in the unprivileged user + mount namespace
mount --move /mnt/aaa /opt
Unfortunately, this is a pretty big deal for userspace since this is
e.g. used to inject mounts into running unprivileged containers.
So this regression really needs to go away rather quickly.
The problem is that a recent change falsely locked the root of the newly
added mounts by setting MNT_LOCKED. Fix this by only locking the mounts
on copy_mnt_ns() and not when adding a new mount.
Fixes: 3bd045cc9c ("separate copying and locking mount tree on cross-userns copies")
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: <stable@vger.kernel.org>
Tested-by: Christian Brauner <christian@brauner.io>
Acked-by: Christian Brauner <christian@brauner.io>
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: Christian Brauner <christian@brauner.io>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Based on 1 normalized pattern(s):
released under gpl v2
extracted by the scancode license scanner the SPDX license identifier
GPL-2.0-only
has been chosen to replace the boilerplate/reference in 15 file(s).
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Steve Winslow <swinslow@gmail.com>
Reviewed-by: Allison Randal <allison@lohutok.net>
Reviewed-by: Alexios Zavras <alexios.zavras@intel.com>
Cc: linux-spdx@vger.kernel.org
Link: https://lkml.kernel.org/r/20190528171438.895196075@linutronix.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Only the mount namespace code that implements mount(2) should be using the
MS_* flags. Suppress them inside the kernel unless uapi/linux/mount.h is
included.
Signed-off-by: David Howells <dhowells@redhat.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Reviewed-by: David Howells <dhowells@redhat.com>
Andrei Vagin pointed out that time to executue propagate_umount can go
non-linear (and take a ludicrious amount of time) when the mount
propogation trees of the mounts to be unmunted by a lazy unmount
overlap.
Make the walk of the mount propagation trees nearly linear by
remembering which mounts have already been visited, allowing
subsequent walks to detect when walking a mount propgation tree or a
subtree of a mount propgation tree would be duplicate work and to skip
them entirely.
Walk the list of mounts whose propgatation trees need to be traversed
from the mount highest in the mount tree to mounts lower in the mount
tree so that odds are higher that the code will walk the largest trees
first, allowing later tree walks to be skipped entirely.
Add cleanup_umount_visitation to remover the code's memory of which
mounts have been visited.
Add the functions last_slave and skip_propagation_subtree to allow
skipping appropriate parts of the mount propagation tree without
needing to change the logic of the rest of the code.
A script to generate overlapping mount propagation trees:
$ cat runs.h
set -e
mount -t tmpfs zdtm /mnt
mkdir -p /mnt/1 /mnt/2
mount -t tmpfs zdtm /mnt/1
mount --make-shared /mnt/1
mkdir /mnt/1/1
iteration=10
if [ -n "$1" ] ; then
iteration=$1
fi
for i in $(seq $iteration); do
mount --bind /mnt/1/1 /mnt/1/1
done
mount --rbind /mnt/1 /mnt/2
TIMEFORMAT='%Rs'
nr=$(( ( 2 ** ( $iteration + 1 ) ) + 1 ))
echo -n "umount -l /mnt/1 -> $nr "
time umount -l /mnt/1
nr=$(cat /proc/self/mountinfo | grep zdtm | wc -l )
time umount -l /mnt/2
$ for i in $(seq 9 19); do echo $i; unshare -Urm bash ./run.sh $i; done
Here are the performance numbers with and without the patch:
mhash | 8192 | 8192 | 1048576 | 1048576
mounts | before | after | before | after
------------------------------------------------
1025 | 0.040s | 0.016s | 0.038s | 0.019s
2049 | 0.094s | 0.017s | 0.080s | 0.018s
4097 | 0.243s | 0.019s | 0.206s | 0.023s
8193 | 1.202s | 0.028s | 1.562s | 0.032s
16385 | 9.635s | 0.036s | 9.952s | 0.041s
32769 | 60.928s | 0.063s | 44.321s | 0.064s
65537 | | 0.097s | | 0.097s
131073 | | 0.233s | | 0.176s
262145 | | 0.653s | | 0.344s
524289 | | 2.305s | | 0.735s
1048577 | | 7.107s | | 2.603s
Andrei Vagin reports fixing the performance problem is part of the
work to fix CVE-2016-6213.
Cc: stable@vger.kernel.org
Fixes: a05964f391 ("[PATCH] shared mounts handling: umount")
Reported-by: Andrei Vagin <avagin@openvz.org>
Reviewed-by: Andrei Vagin <avagin@virtuozzo.com>
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
While investigating some poor umount performance I realized that in
the case of overlapping mount trees where some of the mounts are locked
the code has been failing to unmount all of the mounts it should
have been unmounting.
This failure to unmount all of the necessary
mounts can be reproduced with:
$ cat locked_mounts_test.sh
mount -t tmpfs test-base /mnt
mount --make-shared /mnt
mkdir -p /mnt/b
mount -t tmpfs test1 /mnt/b
mount --make-shared /mnt/b
mkdir -p /mnt/b/10
mount -t tmpfs test2 /mnt/b/10
mount --make-shared /mnt/b/10
mkdir -p /mnt/b/10/20
mount --rbind /mnt/b /mnt/b/10/20
unshare -Urm --propagation unchaged /bin/sh -c 'sleep 5; if [ $(grep test /proc/self/mountinfo | wc -l) -eq 1 ] ; then echo SUCCESS ; else echo FAILURE ; fi'
sleep 1
umount -l /mnt/b
wait %%
$ unshare -Urm ./locked_mounts_test.sh
This failure is corrected by removing the prepass that marks mounts
that may be umounted.
A first pass is added that umounts mounts if possible and if not sets
mount mark if they could be unmounted if they weren't locked and adds
them to a list to umount possibilities. This first pass reconsiders
the mounts parent if it is on the list of umount possibilities, ensuring
that information of umoutability will pass from child to mount parent.
A second pass then walks through all mounts that are umounted and processes
their children unmounting them or marking them for reparenting.
A last pass cleans up the state on the mounts that could not be umounted
and if applicable reparents them to their first parent that remained
mounted.
While a bit longer than the old code this code is much more robust
as it allows information to flow up from the leaves and down
from the trunk making the order in which mounts are encountered
in the umount propgation tree irrelevant.
Cc: stable@vger.kernel.org
Fixes: 0c56fe3142 ("mnt: Don't propagate unmounts to locked mounts")
Reviewed-by: Andrei Vagin <avagin@virtuozzo.com>
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Ever since mount propagation was introduced in cases where a mount in
propagated to parent mount mountpoint pair that is already in use the
code has placed the new mount behind the old mount in the mount hash
table.
This implementation detail is problematic as it allows creating
arbitrary length mount hash chains.
Furthermore it invalidates the constraint maintained elsewhere in the
mount code that a parent mount and a mountpoint pair will have exactly
one mount upon them. Making it hard to deal with and to talk about
this special case in the mount code.
Modify mount propagation to notice when there is already a mount at
the parent mount and mountpoint where a new mount is propagating to
and place that preexisting mount on top of the new mount.
Modify unmount propagation to notice when a mount that is being
unmounted has another mount on top of it (and no other children), and
to replace the unmounted mount with the mount on top of it.
Move the MNT_UMUONT test from __lookup_mnt_last into
__propagate_umount as that is the only call of __lookup_mnt_last where
MNT_UMOUNT may be set on any mount visible in the mount hash table.
These modifications allow:
- __lookup_mnt_last to be removed.
- attach_shadows to be renamed __attach_mnt and its shadow
handling to be removed.
- commit_tree to be simplified
- copy_tree to be simplified
The result is an easier to understand tree of mounts that does not
allow creation of arbitrary length hash chains in the mount hash table.
The result is also a very slight userspace visible difference in semantics.
The following two cases now behave identically, where before order
mattered:
case 1: (explicit user action)
B is a slave of A
mount something on A/a , it will propagate to B/a
and than mount something on B/a
case 2: (tucked mount)
B is a slave of A
mount something on B/a
and than mount something on A/a
Histroically umount A/a would fail in case 1 and succeed in case 2.
Now umount A/a succeeds in both configurations.
This very small change in semantics appears if anything to be a bug
fix to me and my survey of userspace leads me to believe that no programs
will notice or care of this subtle semantic change.
v2: Updated to mnt_change_mountpoint to not call dput or mntput
and instead to decrement the counts directly. It is guaranteed
that there will be other references when mnt_change_mountpoint is
called so this is safe.
v3: Moved put_mountpoint under mount_lock in attach_recursive_mnt
As the locking in fs/namespace.c changed between v2 and v3.
v4: Reworked the logic in propagate_mount_busy and __propagate_umount
that detects when a mount completely covers another mount.
v5: Removed unnecessary tests whose result is alwasy true in
find_topper and attach_recursive_mnt.
v6: Document the user space visible semantic difference.
Cc: stable@vger.kernel.org
Fixes: b90fa9ae8f ("[PATCH] shared mount handling: bind and rbind")
Tested-by: Andrei Vagin <avagin@virtuozzo.com>
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Make sure that clone_mnt() never returns a mount with MNT_SHARED in
flags, but without a valid ->mnt_group_id. That allows to demystify
do_make_slave() quite a bit, among other things.
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
CAI Qian <caiqian@redhat.com> pointed out that the semantics
of shared subtrees make it possible to create an exponentially
increasing number of mounts in a mount namespace.
mkdir /tmp/1 /tmp/2
mount --make-rshared /
for i in $(seq 1 20) ; do mount --bind /tmp/1 /tmp/2 ; done
Will create create 2^20 or 1048576 mounts, which is a practical problem
as some people have managed to hit this by accident.
As such CVE-2016-6213 was assigned.
Ian Kent <raven@themaw.net> described the situation for autofs users
as follows:
> The number of mounts for direct mount maps is usually not very large because of
> the way they are implemented, large direct mount maps can have performance
> problems. There can be anywhere from a few (likely case a few hundred) to less
> than 10000, plus mounts that have been triggered and not yet expired.
>
> Indirect mounts have one autofs mount at the root plus the number of mounts that
> have been triggered and not yet expired.
>
> The number of autofs indirect map entries can range from a few to the common
> case of several thousand and in rare cases up to between 30000 and 50000. I've
> not heard of people with maps larger than 50000 entries.
>
> The larger the number of map entries the greater the possibility for a large
> number of active mounts so it's not hard to expect cases of a 1000 or somewhat
> more active mounts.
So I am setting the default number of mounts allowed per mount
namespace at 100,000. This is more than enough for any use case I
know of, but small enough to quickly stop an exponential increase
in mounts. Which should be perfect to catch misconfigurations and
malfunctioning programs.
For anyone who needs a higher limit this can be changed by writing
to the new /proc/sys/fs/mount-max sysctl.
Tested-by: CAI Qian <caiqian@redhat.com>
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
When the first propgated copy was a slave the following oops would result:
> BUG: unable to handle kernel NULL pointer dereference at 0000000000000010
> IP: [<ffffffff811fba4e>] propagate_one+0xbe/0x1c0
> PGD bacd4067 PUD bac66067 PMD 0
> Oops: 0000 [#1] SMP
> Modules linked in:
> CPU: 1 PID: 824 Comm: mount Not tainted 4.6.0-rc5userns+ #1523
> Hardware name: Bochs Bochs, BIOS Bochs 01/01/2007
> task: ffff8800bb0a8000 ti: ffff8800bac3c000 task.ti: ffff8800bac3c000
> RIP: 0010:[<ffffffff811fba4e>] [<ffffffff811fba4e>] propagate_one+0xbe/0x1c0
> RSP: 0018:ffff8800bac3fd38 EFLAGS: 00010283
> RAX: 0000000000000000 RBX: ffff8800bb77ec00 RCX: 0000000000000010
> RDX: 0000000000000000 RSI: ffff8800bb58c000 RDI: ffff8800bb58c480
> RBP: ffff8800bac3fd48 R08: 0000000000000001 R09: 0000000000000000
> R10: 0000000000001ca1 R11: 0000000000001c9d R12: 0000000000000000
> R13: ffff8800ba713800 R14: ffff8800bac3fda0 R15: ffff8800bb77ec00
> FS: 00007f3c0cd9b7e0(0000) GS:ffff8800bfb00000(0000) knlGS:0000000000000000
> CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
> CR2: 0000000000000010 CR3: 00000000bb79d000 CR4: 00000000000006e0
> Stack:
> ffff8800bb77ec00 0000000000000000 ffff8800bac3fd88 ffffffff811fbf85
> ffff8800bac3fd98 ffff8800bb77f080 ffff8800ba713800 ffff8800bb262b40
> 0000000000000000 0000000000000000 ffff8800bac3fdd8 ffffffff811f1da0
> Call Trace:
> [<ffffffff811fbf85>] propagate_mnt+0x105/0x140
> [<ffffffff811f1da0>] attach_recursive_mnt+0x120/0x1e0
> [<ffffffff811f1ec3>] graft_tree+0x63/0x70
> [<ffffffff811f1f6b>] do_add_mount+0x9b/0x100
> [<ffffffff811f2c1a>] do_mount+0x2aa/0xdf0
> [<ffffffff8117efbe>] ? strndup_user+0x4e/0x70
> [<ffffffff811f3a45>] SyS_mount+0x75/0xc0
> [<ffffffff8100242b>] do_syscall_64+0x4b/0xa0
> [<ffffffff81988f3c>] entry_SYSCALL64_slow_path+0x25/0x25
> Code: 00 00 75 ec 48 89 0d 02 22 22 01 8b 89 10 01 00 00 48 89 05 fd 21 22 01 39 8e 10 01 00 00 0f 84 e0 00 00 00 48 8b 80 d8 00 00 00 <48> 8b 50 10 48 89 05 df 21 22 01 48 89 15 d0 21 22 01 8b 53 30
> RIP [<ffffffff811fba4e>] propagate_one+0xbe/0x1c0
> RSP <ffff8800bac3fd38>
> CR2: 0000000000000010
> ---[ end trace 2725ecd95164f217 ]---
This oops happens with the namespace_sem held and can be triggered by
non-root users. An all around not pleasant experience.
To avoid this scenario when finding the appropriate source mount to
copy stop the walk up the mnt_master chain when the first source mount
is encountered.
Further rewrite the walk up the last_source mnt_master chain so that
it is clear what is going on.
The reason why the first source mount is special is that it it's
mnt_parent is not a mount in the dest_mnt propagation tree, and as
such termination conditions based up on the dest_mnt mount propgation
tree do not make sense.
To avoid other kinds of confusion last_dest is not changed when
computing last_source. last_dest is only used once in propagate_one
and that is above the point of the code being modified, so changing
the global variable is meaningless and confusing.
Cc: stable@vger.kernel.org
fixes: f2ebb3a921 ("smarter propagate_mnt()")
Reported-by: Tycho Andersen <tycho.andersen@canonical.com>
Reviewed-by: Seth Forshee <seth.forshee@canonical.com>
Tested-by: Seth Forshee <seth.forshee@canonical.com>
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
propagate_one(m) calculates "type" argument for copy_tree() like this:
> if (m->mnt_group_id == last_dest->mnt_group_id) {
> type = CL_MAKE_SHARED;
> } else {
> type = CL_SLAVE;
> if (IS_MNT_SHARED(m))
> type |= CL_MAKE_SHARED;
> }
The "type" argument then governs clone_mnt() behavior with respect to flags
and mnt_master of new mount. When we iterate through a slave group, it is
possible that both current "m" and "last_dest" are not shared (although,
both are slaves, i.e. have non-NULL mnt_master-s). Then the comparison
above erroneously makes new mount shared and sets its mnt_master to
last_source->mnt_master. The patch fixes the problem by handling zero
mnt_group_id-s as though they are unequal.
The similar problem exists in the implementation of "else" clause above
when we have to ascend upward in the master/slave tree by calling:
> last_source = last_source->mnt_master;
> last_dest = last_source->mnt_parent;
proper number of times. The last step is governed by
"n->mnt_group_id != last_dest->mnt_group_id" condition that may lie if
both are zero. The patch fixes this case in the same way as the former one.
[AV: don't open-code an obvious helper...]
Signed-off-by: Maxim Patlasov <mpatlasov@virtuozzo.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
If the first mount in shared subtree is locked don't unmount the
shared subtree.
This is ensured by walking through the mounts parents before children
and marking a mount as unmountable if it is not locked or it is locked
but it's parent is marked.
This allows recursive mount detach to propagate through a set of
mounts when unmounting them would not reveal what is under any locked
mount.
Cc: stable@vger.kernel.org
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
A prerequisite of calling umount_tree is that the point where the tree
is mounted at is valid to unmount.
If we are propagating the effect of the unmount clear MNT_LOCKED in
every instance where the same filesystem is mounted on the same
mountpoint in the mount tree, as we know (by virtue of the fact
that umount_tree was called) that it is safe to reveal what
is at that mountpoint.
Cc: stable@vger.kernel.org
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
- Modify __lookup_mnt_hash_last to ignore mounts that have MNT_UMOUNTED set.
- Don't remove mounts from the mount hash table in propogate_umount
- Don't remove mounts from the mount hash table in umount_tree before
the entire list of mounts to be umounted is selected.
- Remove mounts from the mount hash table as the last thing that
happens in the case where a mount has a parent in umount_tree.
Mounts without parents are not hashed (by definition).
This paves the way for delaying removal from the mount hash table even
farther and fixing the MNT_LOCKED vs MNT_DETACH issue.
Cc: stable@vger.kernel.org
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
In some instances it is necessary to know if the the unmounting
process has begun on a mount. Add MNT_UMOUNT to make that reliably
testable.
This fix gets used in fixing locked mounts in MNT_DETACH
Cc: stable@vger.kernel.org
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
umount_tree builds a list of mounts that need to be unmounted.
Utilize mnt_list for this purpose instead of mnt_hash. This begins to
allow keeping a mount on the mnt_hash after it is unmounted, which is
necessary for a properly functioning MNT_LOCKED implementation.
The fact that mnt_list is an ordinary list makding available list_move
is nice bonus.
Cc: stable@vger.kernel.org
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Clear MNT_LOCKED in the callers of copy_tree except copy_mnt_ns, and
collect_mounts. In copy_mnt_ns it is necessary to create an exact
copy of a mount tree, so not clearing MNT_LOCKED is important.
Similarly collect_mounts is used to take a snapshot of the mount tree
for audit logging purposes and auditing using a faithful copy of the
tree is important.
This becomes particularly significant when we start setting MNT_LOCKED
on rootfs to prevent it from being unmounted.
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
The check in __propagate_umount() ("has somebody explicitly mounted
something on that slave?") is done *before* taking the already doomed
victims out of the child lists.
Cc: stable@vger.kernel.org
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
The current mainline has copies propagated to *all* nodes, then
tears down the copies we made for nodes that do not contain
counterparts of the desired mountpoint. That sets the right
propagation graph for the copies (at teardown time we move
the slaves of removed node to a surviving peer or directly
to master), but we end up paying a fairly steep price in
useless allocations. It's fairly easy to create a situation
where N calls of mount(2) create exactly N bindings, with
O(N^2) vfsmounts allocated and freed in process.
Fortunately, it is possible to avoid those allocations/freeings.
The trick is to create copies in the right order and find which
one would've eventually become a master with the current algorithm.
It turns out to be possible in O(nodes getting propagation) time
and with no extra allocations at all.
One part is that we need to make sure that eventual master will be
created before its slaves, so we need to walk the propagation
tree in a different order - by peer groups. And iterate through
the peers before dealing with the next group.
Another thing is finding the (earlier) copy that will be a master
of one we are about to create; to do that we are (temporary) marking
the masters of mountpoints we are attaching the copies to.
Either we are in a peer of the last mountpoint we'd dealt with,
or we have the following situation: we are attaching to mountpoint M,
the last copy S_0 had been attached to M_0 and there are sequences
S_0...S_n, M_0...M_n such that S_{i+1} is a master of S_{i},
S_{i} mounted on M{i} and we need to create a slave of the first S_{k}
such that M is getting propagation from M_{k}. It means that the master
of M_{k} will be among the sequence of masters of M. On the
other hand, the nearest marked node in that sequence will either
be the master of M_{k} or the master of M_{k-1} (the latter -
in the case if M_{k-1} is a slave of something M gets propagation
from, but in a wrong peer group).
So we go through the sequence of masters of M until we find
a marked one (P). Let N be the one before it. Then we go through
the sequence of masters of S_0 until we find one (say, S) mounted
on a node D that has P as master and check if D is a peer of N.
If it is, S will be the master of new copy, if not - the master of S
will be.
That's it for the hard part; the rest is fairly simple. Iterator
is in next_group(), handling of one prospective mountpoint is
propagate_one().
It seems to survive all tests and gives a noticably better performance
than the current mainline for setups that are seriously using shared
subtrees.
Cc: stable@vger.kernel.org
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
fixes RCU bug - walking through hlist is safe in face of element moves,
since it's self-terminating. Cyclic lists are not - if we end up jumping
to another hash chain, we'll loop infinitely without ever hitting the
original list head.
[fix for dumb braino folded]
Spotted by: Max Kellermann <mk@cm4all.com>
Cc: stable@vger.kernel.org
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Instead of passing the direction as argument (and checking it on every
step through the hash chain), just have separate __lookup_mnt() and
__lookup_mnt_last(). And use the standard iterators...
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
aka br_write_{lock,unlock} of vfsmount_lock. Inlines in fs/mount.h,
vfsmount_lock extern moved over there as well.
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
When the group id of a shared mount is not allocated, the umount still
tries to call mnt_release_group_id(), which eventually hits a kernel
warning at ida_remove() spewing a message like:
ida_remove called for id=0 which is not allocated.
This patch fixes the bug simply checking the group id in the caller.
Reported-by: Cristian Rodríguez <crrodriguez@opensuse.org>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Pull VFS updates from Al Viro,
Misc cleanups all over the place, mainly wrt /proc interfaces (switch
create_proc_entry to proc_create(), get rid of the deprecated
create_proc_read_entry() in favor of using proc_create_data() and
seq_file etc).
7kloc removed.
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs: (204 commits)
don't bother with deferred freeing of fdtables
proc: Move non-public stuff from linux/proc_fs.h to fs/proc/internal.h
proc: Make the PROC_I() and PDE() macros internal to procfs
proc: Supply a function to remove a proc entry by PDE
take cgroup_open() and cpuset_open() to fs/proc/base.c
ppc: Clean up scanlog
ppc: Clean up rtas_flash driver somewhat
hostap: proc: Use remove_proc_subtree()
drm: proc: Use remove_proc_subtree()
drm: proc: Use minor->index to label things, not PDE->name
drm: Constify drm_proc_list[]
zoran: Don't print proc_dir_entry data in debug
reiserfs: Don't access the proc_dir_entry in r_open(), r_start() r_show()
proc: Supply an accessor for getting the data from a PDE's parent
airo: Use remove_proc_subtree()
rtl8192u: Don't need to save device proc dir PDE
rtl8187se: Use a dir under /proc/net/r8180/
proc: Add proc_mkdir_data()
proc: Move some bits from linux/proc_fs.h to linux/{of.h,signal.h,tty.h}
proc: Move PDE_NET() to fs/proc/proc_net.c
...
As a matter of policy MNT_READONLY should not be changable if the
original mounter had more privileges than creator of the mount
namespace.
Add the flag CL_UNPRIVILEGED to note when we are copying a mount from
a mount namespace that requires more privileges to a mount namespace
that requires fewer privileges.
When the CL_UNPRIVILEGED flag is set cause clone_mnt to set MNT_NO_REMOUNT
if any of the mnt flags that should never be changed are set.
This protects both mount propagation and the initial creation of a less
privileged mount namespace.
Cc: stable@vger.kernel.org
Acked-by: Serge Hallyn <serge.hallyn@canonical.com>
Reported-by: Andy Lutomirski <luto@amacapital.net>
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
copy_tree() can theoretically fail in a case other than ENOMEM, but always
returns NULL which is interpreted by callers as -ENOMEM. Change it to return
an explicit error.
Also change clone_mnt() for consistency and because union mounts will add new
error cases.
Thanks to Andreas Gruenbacher <agruen@suse.de> for a bug fix.
[AV: folded braino fix by Dan Carpenter]
Original-author: Valerie Aurora <vaurora@redhat.com>
Signed-off-by: David Howells <dhowells@redhat.com>
Cc: Valerie Aurora <valerie.aurora@gmail.com>
Cc: Andreas Gruenbacher <agruen@suse.de>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
lglocks and brlocks are currently generated with some complicated macros
in lglock.h. But there's no reason to not just use common utility
functions and put all the data into a common data structure.
In preparation, this patch changes the API to look more like normal
function calls with pointers, not magic macros.
The patch is rather large because I move over all users in one go to keep
it bisectable. This impacts the VFS somewhat in terms of lines changed.
But no actual behaviour change.
[akpm@linux-foundation.org: checkpatch fixes]
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Rusty Russell <rusty@rustcorp.com.au>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Christian Brauner